http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Extraction of Different Types of Geometrical Features from Raw Sensor Data of Two-dimensional LRF
염서군,무경,원조,한창수,Yan, Rui-Jun,Wu, Jing,Yuan, Chao,Han, Chang-Soo Institute of Control 2015 제어·로봇·시스템학회 논문지 Vol.21 No.3
This paper describes extraction methods of five different types of geometrical features (line, arc, corner, polynomial curve, NURBS curve) from the obtained raw data by using a two-dimensional laser range finder (LRF). Natural features with their covariance matrices play a key role in the realization of feature-based simultaneous localization and mapping (SLAM), which can be used to represent the environment and correct the pose of mobile robot. The covariance matrices of these geometrical features are derived in detail based on the raw sensor data and the uncertainty of LRF. Several comparison are made and discussed to highlight the advantages and drawbacks of each type of geometrical feature. Finally, the extracted features from raw sensor data obtained by using a LRF in an indoor environment are used to validate the proposed extraction methods.
누적 센서 데이터 갱신을 이용한 아크/라인 세그먼트 기반 SLAM
염서군,최윤성,무경,한창수,Yan, Rui-Jun,Choi, Youn-sung,Wu, Jing,Han, Chang-soo 제어로봇시스템학회 2015 제어·로봇·시스템학회 논문지 Vol.21 No.10
This paper presents arc/line segments-based Simultaneous Localization and Mapping (SLAM) by updating accumulated laser sensor data with a mobile robot moving in an unknown environment. For each scan, the sensor data in the set are stored by a small constant number of parameters that can recover the necessary information contained in the raw data of the group. The arc and line segments are then extracted according to different limit values, but based on the same parameters. If two segments, whether they are homogenous features or not, from two scans are matched successfully, the new segment is extracted from the union set with combined data information obtained by means of summing the equivalent parameters of these two sets, not combining the features directly. The covariance matrixes of the segments are also updated and calculated synchronously employing the same parameters. The experiment results obtained in an irregular indoor environment show the good performance of the proposed method.
Extraction of Different Types of Geometrical Features from Raw Sensor Data of Two-dimensional LRF
Rui-Jun Yan(염서군),Jing Wu(무경),Chao Yuan(원조),Chang-Soo Han(한창수) 제어로봇시스템학회 2015 제어·로봇·시스템학회 논문지 Vol.21 No.3
This paper describes extraction methods of five different types of geometrical features (line, arc, corner, polynomial curve, NURBS curve) from the obtained raw data by using a two-dimensional laser range finder (LRF). Natural features with their covariance matrices play a key role in the realization of feature-based simultaneous localization and mapping (SLAM), which can be used to represent the environment and correct the pose of mobile robot. The covariance matrices of these geometrical features are derived in detail based on the raw sensor data and the uncertainty of LRF. Several comparison are made and discussed to highlight the advantages and drawbacks of each type of geometrical feature. Finally, the extracted features from raw sensor data obtained by using a LRF in an indoor environment are used to validate the proposed extraction methods.
누적 센서 데이터 갱신을 이용한 아크/라인 세그먼트 기반 SLAM
염서군(Rui-Jun Yan),최윤성(Youn-sung Choi),무경(Jing Wu),한창수(Chang-soo Han) 제어로봇시스템학회 2015 제어·로봇·시스템학회 논문지 Vol.18 No.12
This paper presents arc/line segments-based Simultaneous Localization and Mapping (SLAM) by updating accumulated laser sensor data with a mobile robot moving in an unknown environment. For each scan, the sensor data in the set are stored by a small constant number of parameters that can recover the necessary information contained in the raw data of the group. The arc and line segments are then extracted according to different limit values, but based on the same parameters. If two segments, whether they are homogenous features or not, from two scans are matched successfully, the new segment is extracted from the union set with combined data information obtained by means of summing the equivalent parameters of these two sets, not combining the features directly. The covariance matrixes of the segments are also updated and calculated synchronously employing the same parameters. The experiment results obtained in an irregular indoor environment show the good performance of the proposed method.